Remove Links

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the agent knows this is an irreversible-feeling write. The description adds one genuinely useful trait beyond that — the dry_run preview path — but says nothing about reversibility, whether linked elements survive, or scope of deletion.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence with the destructive action front-loaded and the safety hint trailing. Nothing is padded, though for a five-parameter destructive tool the extreme terseness edges toward under-specification rather than economy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with five parameters and only 20% schema coverage, the description omits the filter (kinds), the CAD-import flag, and the document-disambiguation requirement documented only in the schema. Output schema exists so return values need no explanation, but input-side completeness is clearly lacking.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% (just the 'document' param), so the description carries the burden for the other four. 'Link types' loosely maps to kinds and 'instances' to links, but the accepted forms of links (names/IDs/'*'), the kinds enum, include_imported_cad, and document disambiguation are all unexplained in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Delete selected link types and their instances.' This distinguishes it from revit_links_status (read) and the generic revit_delete. However, 'selected' is left undefined and the tool is not contrasted with revit_delete, which also removes model content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only guidance is procedural: 'preview with dry_run,' which implies you should dry-run before committing. There is no statement of when to use this tool versus revit_delete, revit_links_status, or revit_compare_link_datums, and no prerequisites such as needing an open document.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.